Profile Job Results
Jobs
jpv684vz5
Results Ready
Name
whisper_small_en_WhisperDecoder
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[12, 12, 64, 1500]v_cache_cross: float32[12, 12, 1500, 64]k_cache_self: float32[12, 12, 64, 224]v_cache_self: float32[12, 12, 224, 64]Completion Time
1/8/2025, 1:46:46 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 15 (AQ3A.240829.003)
- Build ID: Pakala.LA.1.0.r1-01032-STD.PROD-1
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
18.2 ms
Estimated Peak Memory Usage
16 ‑ 176 MB
Compute Units
NPU
2573
| Stage | Time | Memory |
|---|---|---|
First App Load | 22.3 s | 3 GB |
Subsequent App Load | 21.5 s | 3‑4 GB |
Inference | 18.2 ms | 16‑176 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device